© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 30060
    Prev
    Next
    INDEX
    Explanations

    high temperature, heat, heating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĨ·æ°´
    -0.09
    åĩī
    -0.09
    浸
    -0.09
    æ¡´
    -0.09
     Flor
    -0.09
    èī¯å¥½
    -0.08
    çĦĺ
    -0.08
    ç¿ĺ
    -0.08
    acers
    -0.08
    èµ°
    -0.08
    POSITIVE LOGITS
    足以
    0.11
    obel
    0.10
    å¹Ħ
    0.10
    å¢ĻéĿ¢
    0.10
    ä¸Ģç¬ij
    0.09
    æijĦ
    0.09
    失æݧ
    0.09
    å°Ĭ
    0.09
    æ½Ń
    0.08
     Stuff
    0.08
    Activations Density 0.093%

    No Known Activations